Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1593 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1288581 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0579. Min Act: -0.0002

Data Index: 149178 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0542. Min Act: -0.0002

Data Index: 571485 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0480. Min Act: -0.0002

Data Index: 658717 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0479. Min Act: -0.0001

Data Index: 326534 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1027468 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0475. Min Act: -0.0002

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1046206 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1114008 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0471. Min Act: -0.0002

Data Index: 495460 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1002731 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1021172 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0450. Min Act: -0.0002

Data Index: 588975 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1294987 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1241603 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0431. Min Act: -0.0002

Data Index: 853388 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0429. Min Act: -0.0002

Data Index: 134430 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0426. Min Act: -0.0002

Data Index: 794398 (C4 (Web Text))

Max Activating Token Index: 1007